Skip to main content
Run failproofai without arguments to start the bundled dashboard at http://localhost:8020. It reads local agent histories, policy configuration, audit results, and hook activity directly from the machine. The local dashboard is separate from Failproof AI Cloud. It works without a Cloud account and does not prove that events were delivered to your organization.

​
Dashboard areas

​
Review policy activity

  1. Open Policies → Activity and set the decision and source filters.
  2. Narrow by event, harness, tool, or policy name.
  3. Expand a row to inspect its reason, matched policies, source, execution mode, and duration.
  4. Follow the session link to place the decision in transcript context.
A denied-looking row can still be observational on a harness/event pair that does not consume blocking verdicts. The detail view calls out verified enforcement capability.

​
Configure policies locally

  1. Open Policies → Configure and choose the harnesses and configuration scope.
  2. Enable a builtin or discovered custom policy.
  3. For a parameterized builtin, open its configuration control and save supported values.
  4. Return to Activity and run matching and non-matching actions.
Convention policies show their project or user source. Explicit custom-path changes may require rerunning CLI configuration so the selected path is recorded.

​
Browse projects and sessions

The Projects page combines supported local history stores. Select a project to list its sessions, then open a session for the raw log viewer, subagent segments, download action, and session-scoped policy activity. If a project or session is missing, confirm the harness uses its default history location or register an extra root with failproofai harness add-path.

​
Set up Jev

The Settings page’s Jev section writes the same ~/.failproofai/jev.json that failproofai jev setup writes, validated by the loader’s own rules, so the hooks use it on their next call. It says whether Jev is on and in which mode, and — once it is on — how many calls it answered and how often it fell back to the regex policies. Failproof AI ships no Jev checks: while no installed pack declares any, the section says so and names failproofai policies add FailproofAI/jev-policies, and Jev asks nothing.
  • Your own endpoint. Choose the provider, give an endpoint URL for custom (optional for the others) and an account id for Cloudflare, paste the token, and pick the mode (observe, enforce or off). The token is write-only: the page never shows it, and leaving the field blank keeps the stored one while the provider and the endpoint’s host stay the same. Change either and the page asks for the token again, so a stored key is never sent somewhere it was not given for. See Jev with your own key.
  • FailproofAI Cloud. Jev through Cloud is turned on by connecting the machine (failproofai config --token <key>); the page offers only its on/off switch and mode. See Jev through FailproofAI Cloud.
A config whose key comes from FAILPROOFAI_JEV_API_KEY (jev setup --key-from-env) is judged from the dashboard’s own environment, which may not be the one your agent runs in; run failproofai jev status where the agent runs to see what its hooks do.

​
Schedule offline audits

Open Settings, enable scheduled scanning, choose its supported interval, and configure report delivery when available. The page reports the next run, last run, exit code, and whether the background daemon is supported on the platform.
The local dashboard can display prompts, tool input, file content, and terminal output from local agent histories. Bind it only to trusted interfaces and stop the process when review is complete.